Update app.py

app.py

@@ -9,7 +9,7 @@ login(token, add_to_git_credential=True,write_permission=True )
 model = joblib.load('arabic_text_classifier.pkl')
 vectorizer = joblib.load('tfidf_vectorizer.pkl')
 label_encoder = joblib.load('label_encoder.pkl')
-
+available_labels = label_encoder.classes_
 def predict_category(text):
     text_vector = vectorizer.transform([text])
     probabilities = model.predict_proba(text_vector)[0]
@@ -43,7 +43,27 @@ def classify_and_flag(text):
     return prediction
 
 
-interface = gr.Interface(fn=classify_and_flag, inputs=gr.Textbox(lines=5, placeholder= "Enter text in Arabic here...", label="Text" ), outputs=gr.Label(label="text"), 
-                         title="Arabic Text Classifier", description="Classify Arabic text into categories bu using Logistic Regression")
+interface = gr.Interface(fn=classify_and_flag, 
+                         inputs=gr.Textbox(lines=5, placeholder= "Enter text in Arabic here...", label="Text" ), 
+                         outputs=gr.Label(label="Predicted Category"), 
+                         title="Arabic Text Classifier", 
+                         description="""
+    This interface allows you to classify Arabic text into different categories using a machine learning model trained on 190,000 real-world text samples.
+    
+    **Model Overview**:
+    - The model is based on **Logistic Regression**, a simple but effective machine learning algorithm often used for text classification tasks.
+    - It was trained on a large dataset of **190,000 Arabic text entries**, ensuring robustness and accuracy in classifying Arabic text.
+
+    **How to use**:
+    - Enter any Arabic text in the input box or select one of the provided examples.
+    - The model will predict the category that the text most likely belongs to.
+    - If the model is uncertain, it will classify the text as 'Other'.
+    
+    **Available Labels**:
+    The model can predict the following categories:
+    - {}
+    
+    Try entering some text in Arabic or select one of the provided examples to see how the model works.
+    """.format(", ".join(available_labels)),theme="ParityError/Interstellar")
 
 interface.launch()